基于改进证据理论的轨道电路故障诊断方法

Fault diagnosis method of track circuit based on improved evidence theory

为有效地利用轨道电路特征参数来提高轨道电路故障诊断的准确性,提出结合灰色关联分析的改进证据理论信息融合故障诊断方法。构造轨道电路标准模式参数序列,对同一故障的3个待检测样本序列进行灰色关联度计算,并根据灰色关联度获得各证据的基本概率赋值;利用证据距离和不确定度生成权重;将证据进行加权修正,取得合理的重构证据;通过证据理论组合方法将重构证据进行融合,实现轨道电路故障的分类和识别。研究结果表明:该方法的诊断结果优于灰色关联分析法的诊断结果,能明显提高对轨道电路故障诊断的准确率和识别率。

In order to make full use of the characteristic parameters of the track circuit to improve the accuracy of the fault diagnosis of the track circuit,this paper was to propose the fault diagnosis method based on improved evidence theory,which was combined with grey correlation analysis.Firstly,the standard model parameter sequences of track circuit were constructed to calculate the gray correlation degree of the three sequences of samples to be tested for the same fault,and the basic probability assignment of each evidence was obtained according to the grey relational degree.And then not only the distance of evidence but also the uncertainty degree was utilized to generate the weights,and the evidence was weighted corrected to obtain reasonable reconstructed evidence.Finally,the reconstructed evidence was fused by the combination of evidence theory to realize the classification and identification of track circuit faults.The experimental results show that the diagnostic results of this method are superior to those of the gray correlation analysis method only and the accuracy and recognition rate of the fault diagnosis of the track circuit are obviously improved as well.